←back to thread

137 points rezivor | 1 comments | | HN request time: 0s | source

Hey HN! Built this because I was tired of waiting hours for transcription services and didn't want to upload sensitive recordings to the cloud.

  Real metrics from my M1 Max: 4.5hr video file transcribed in 3 minutes 32
  seconds. Works completely offline.

   First 5 HN users who click the button on the page get it free. Literally promo code straight to the app sore  


  Key differences vs Rev/Otter:
  - No 2-hour file limits (handles any length)
  - Timecodes stay accurate on long files (no drift from chunking)
  - Supports MP3, WAV, MP4, MOV, M4A, FLAC
  - Exports to SRT, VTT, JSON, PDF, DOCX, CSV, Markdown

  Built for macOS. Happy to answer questions!
Show context
nubg ◴[] No.45591597[source]
How does it compare to MacWhisper?
replies(1): >>45591639 #
rezivor ◴[] No.45591639[source]
MacWhisper crashes at about an hour of context. This uses, smart, invisible regex in the text generation pipe. Makes this fast. + bonus, there is no context limit
replies(7): >>45591738 #>>45591977 #>>45592072 #>>45593177 #>>45594771 #>>45594799 #>>45595635 #
fl_rn_st ◴[] No.45592072[source]
"Smart, invisible regex" sounds like a lot of bs... could you give a more technical explanation?

Also the Whisper model doesn't really have a context window, it already segments the audio with a certain amount of overlap between the chunks, I really have a hard time understanding what you are trying to say here.

replies(1): >>45592208 #
rezivor ◴[] No.45592208[source]
Whisper will fail > 99%* (edit, most of the time) of the time at lengths over 90 minutes and fairly high over one hour.
replies(4): >>45592339 #>>45592617 #>>45593059 #>>45595625 #
1. saaaaaam ◴[] No.45592617[source]
This is absolutely not my experience. I regularly (weekly at least) use whisper for 90-120 minutes pieces of content and only rarely have problems.